Path Planning and Landing for Unmanned Aerial Vehicles Using AI

Latest trends, societal needs and technological advances have led to an unparalleled expansion in the use of Unmanned Aerial Vehicles (UAV) for military and civilian applications. Such systems are becoming increasingly popular in many operations, since they reduce costs, facilitate activities and can increase the granularity of surveillance or delivery. Beyond the Visual Line of Sight (BVLOS) capabilities are becoming recently a pivotal aspect for the UAV industry, and raise the demand for extended levels of autonomy in order to increase the efficiency of flight operations. The present study examines two main aspects of BVLOS operations, namely trajectory planning and self-landing, and demonstrates how well-established path planning techniques, such as the A* and Dijkstra algorithms, can be used to ensure the shortest trajectory length from point A to point B for a UAV under multiple obstacles and constraints and the least number of error corrections. Extensive simulation results showcase the effectiveness of the proposed method. It also provides evidence of the use of computer vision algorithms for detecting the landing site and assisting the UAV to safely land.